期刊
JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION
卷 116, 期 534, 页码 690-693出版社
TAYLOR & FRANCIS INC
DOI: 10.1080/01621459.2020.1833887
关键词
Covariate shift; Density-ratio estimation; Efficient score; Generalizability
资金
- National Institutes of Health [R01DK108073]
In this study, we discussed the improvement of generalizability in individualized treatment rules and introduced a likelihood-ratio-based method LR-ITR to handle covariate shifts. Numerical studies showed that LR-ITR outperformed CTE-DR-ITR in cases of covariate shift only.
We discuss the results on improving the generalizability of individualized treatment rule following the work by Kallus and Mo et al. We note that the advocated weights in the work of Kallus are connected to the efficient score of the contrast function. We further propose a likelihood-ratio-based method (LR-ITR) to accommodate covariate shifts, and compare it to the CTE-DR-ITR method proposed by Mo et al. We provide the upper-bound on the risk function of the target population when both the covariate shift and the contrast function shift are present. Numerical studies show that LR-ITR can outperform CTE-DR-ITR when there is only covariate shift. for this article are available online.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据